Neural Gradient Regularizer

TL;DR

This paper introduces a neural gradient regularizer (NGR) that models image gradient maps with neural networks, avoiding prior assumptions and outperforming existing methods across various image processing tasks in a versatile, zero-shot manner.

Contribution

The paper proposes a novel neural gradient regularizer that does not rely on sparsity priors, enabling versatile, zero-shot image processing without retraining.

Findings

NGR outperforms state-of-the-art methods in multiple tasks.

NGR is applicable to various image types without retraining.

NGR demonstrates superior edge and detail preservation.

Abstract

Owing to its significant success, the prior imposed on gradient maps has consistently been a subject of great interest in the field of image processing. Total variation (TV), one of the most representative regularizers, is known for its ability to capture the intrinsic sparsity prior underlying gradient maps. Nonetheless, TV and its variants often underestimate the gradient maps, leading to the weakening of edges and details whose gradients should not be zero in the original image (i.e., image structures is not describable by sparse priors of gradient maps). Recently, total deep variation (TDV) has been introduced, assuming the sparsity of feature maps, which provides a flexible regularization learned from large-scale datasets for a specific task. However, TDV requires to retrain the network with image/task variations, limiting its versatility. To alleviate this issue, in this paper, we propose a neural gradient regularizer (NGR) that expresses the gradient map as the output of a neural network. Unlike existing methods, NGR does not rely on any subjective sparsity or other prior assumptions on image gradient maps, thereby avoiding the underestimation of gradient maps. NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer. Extensive experimental results demonstrate the superior performance of NGR over state-of-the-art counterparts for a range of different tasks, further validating its effectiveness and versatility.